© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4704
    Prev
    Next
    INDEX
    Explanations

    text related to a specific instance of a certain class of event

    oai_token-act-pair · gemini-2.0-flash

    fight

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IUrlHelper
    -0.75
    AutoScaleMode
    -0.57
     doInBackground
    -0.56
    олові
    -0.56
     initComponents
    -0.54
    setVerticalGroup
    -0.54
    AccessFile
    -0.52
     ASSERT
    -0.51
     Extragalactic
    -0.49
    StoreMessageInfo
    -0.49
    POSITIVE LOGITS
     fight
    1.23
     fights
    1.12
    fight
    1.02
     fighting
    0.99
     fought
    0.96
    fights
    0.94
     Fight
    0.93
    Fight
    0.92
     Fights
    0.91
     FIGHT
    0.86
    Activations Density 2.190%

    No Known Activations